重庆理工大学学报2024，Vol.38Issue(7)：131-137,7.DOI:10.3969/j.issn.1674-8425(z).2024.04.018
基于Stacking融合的LSTM-SA-RBF短期负荷预测
Stacking fusion based LSTM-SA-RBF short-term load forecasting
摘要
Abstract
To avoid the limitations of individual neural network forecasting and the volatility of time series, this paper proposes a short-term load forecasting model combining singular spectrum analysis (SSA) and stacking framework.First, the strong correlation characteristic factors with historical load are screened by random forest and SSA to reduce noise for load data and simplify the model calculation process.Second, based on the stacking framework, a new combined model is integrated with long- and short-term memory (LSTM) self-attention mechanism(SA) , radial base functions (RBF) neural network and linear regression methods, and cross-validation is employed to avoid model over-fitting.Finally, the PJM and Australian electricity load datasets are adopted for validation.Our simulation results show the proposed model achieves higher prediction accuracy compared with other models.关键词
奇异谱分析/stacking算法/长短期记忆网络/径向基神经网络/短期负荷预测Key words
singular spectrum analysis/stacking algorithm/long and short-term memory network/radial basis neural network/short-term load forecasting分类
信息技术与安全科学引用本文复制引用
方娜,邓心,肖威..基于Stacking融合的LSTM-SA-RBF短期负荷预测[J].重庆理工大学学报,2024,38(7):131-137,7.基金项目
国家自然科学基金青年科学基金项目(51809097) （51809097）
湖北省重点研发计划项目(2021BAA193) （2021BAA193）
